deadtrees.earth - an open, dynamic database for accessing, contributing, analyzing, and visualizing remote sensing-based tree mortality data.
- 1Sensor-based Geoinformatics, University of Freiburg, Freiburg, Germany
- 2Remote Sensing Centre for Earth System Research, Leipzig University, Leipzig, Germany
- 3Deutsches Zentrum für integrative Biodiversitätsforschung (iDiv) Halle-Jena-Leipzig, Leipzig, Germany
- 4School of Environmental Forest Sciences, University of Washington, Washington, USA
- 5Chair of Forest Growth and Dendroecology, University of Freiburg, Germany
- 6Institute for Geography and Geocology (IFGG), Karlsruher Institute of Technology, Germany
- 7Department of Forestry Engineering. University of Córdoba, Spain
- 8Department of Geosciences and Natural Resource, University of Copenhagen, Denmark
- 9Botany Department, Nelson Mandela University, South Africa
- 10Institute of Water and River Basin Management, Karlsruher Institute for Technology, Karlsruhe, Germany
Excessive tree mortality rates prevail in many regions of the world. Understanding tree mortality dynamics remains elusive as this multifaceted phenomenon is influenced by an interplay of abiotic and biotic factors including, but not limited to, global warming, climate extremes, pests, pathogens, and other environmental stressors. Earth observation satellites, coupled with machine learning, present a promising avenue to unravel map standing dead trees and lay the foundation for explaining the underlying dynamics.
However, the lack of globally comprehensive, georeferenced training data spanning various biomes and forest types has hindered the development of a unified global product detailing tree mortality patterns. Present ground-based observations, e.g., sourced from national inventories, are often sparse, lack standardization, and spatial specificity. Alternatively, aerial imagery captured via drones or airplanes in concert with computer vision methods offers a potent resource for mapping standing deadwood with high precision and efficiency on local scales. Such products can subsequently be used to train models based on satellite data to infer standing deadwood on large spatial scales.
In pursuit of harnessing this potential to enhance our global comprehension of tree mortality patterns, we initiated the development of a dynamic database (https://deadtrees.earth), which enables to 1) upload and download aerial imagery with optional labels on standing deadwood, 2) automatically detect (semantic segmentation) standing dead trees in uploaded aerial imagery through a generic detection computer vision model, 3) Visualization and download of extensive spatiotemporal tree mortality products derived from extrapolating standing deadwood using Earth observation data.
This presentation provides an in-depth overview of the deadtrees.earth database, outlining its motivation, current status, and future perspectives. By integrating Earth observation, machine learning, and ground-based data sources, this initiative aims to bridge the existing gaps in understanding global tree mortality dynamics, fostering a comprehensive and accessible resource for researchers and stakeholders alike.
How to cite: Kattenborn, T., Mosig, C., Pratima, K., Frey, J., Perez-Priego, O., Schiefer, F., Cheng, Y., Potts, A., Jehle, J., Mälicke, M., and Mahecha, M.: deadtrees.earth - an open, dynamic database for accessing, contributing, analyzing, and visualizing remote sensing-based tree mortality data., EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-15502, https://doi.org/10.5194/egusphere-egu24-15502, 2024.
